Monte Carlo Search algorithms can give excellent results for some combinatorial optimization problems and for some games. They can be parallelized efficiently on high-end CPU servers. Nested Monte Carlo Search is an algorithm that parallelizes well. We take advantage of this property to obtain large speedups running it on low cost GPUs. The combinatorial optimization problem we use for the experiments is the Snake-in-the-Box. It is a graph theory problem for which Nested Monte Carlo Search previously improved lower bounds. It has applications in electrical engineering, coding theory, and computer network topologies. Using a low cost GPU, we obtain speedups as high as 420 compared to a single CPU.