In this paper, we investigate the antenna selection (AS) problem for scalable video streaming over MIMO wireless networks. By scheduling scalable video layers over MIMO antennas with different signal strength, the video layers are transmitted with un-equal error protections. Considering layer dependencies and various antenna conditions, it is a non-linear combinatorial problem for AS to minimize the overall end-to-end distortion. To find the optimal solution with low complexity, a cross-entropy based solution, named CEBAS, is proposed. All solutions are indexed by unique binary strings, and the primal problem is reformulated to a binary combination problem. Then, random strings are generated using the probability distribution of solutions, which is updated by the cross-entropy optimization method. The feasibility of solution is guaranteed by our proposed projection strategy. CEBAS is iterative in nature and converges to the global optimum in probability. Simulation results reveal both the effectiveness and efficiency of our proposed algorithm. When comparing CEBAS against other existing algorithms, consistent superior performance has been observed.