The lattice Boltzmann method has proven to be a promising method to simulate flow in porous media. Its practical application often relies on parallel computation because of the demand for a large domain and fine grid resolution to adequately resolve pore heterogeneity. The existing domain-decomposition methods for parallel computation usually decompose a domain into a number of subdomains first and then recover the interfaces and perform the load balance. Normally, the interface recovery and the load balance have to be performed iteratively until an acceptable load balance is achieved; this costs time. In this paper we propose a cell-based domain-decomposition method for parallel lattice Boltzmann simulation of flow in porous media. Unlike the existing methods, the cell-based method performs the load balance first to divide the total number of fluid cells into a number of groups (or subdomains), in which the difference of fluid cells in each group is either 0 or 1, depending on if the total number of fluid cells is a multiple of the processor numbers; the interfaces between the subdomains are recovered at last. The cell-based method is to recover the interfaces rather than the load balance; it does not need iteration and gives an exact load balance. The performance of the proposed method is analyzed and compared using different computer systems; the results indicate that it reaches the theoretical parallel efficiency. The method is then applied to simulate flow in a three-dimensional porous medium obtained with microfocus x-ray computed tomography to calculate the permeability, and the result shows good agreement with the experimental data.