With the proliferation of commercial tracking systems, sports data is being generated at an unprecedented speed and the interest in sports play retrieval has grown dramatically as well. However, it is challenging to design an effective, efficient and robust similarity measure for sports play retrieval. To this end, we propose a deep learning approach to learn the representations of sports plays, called play2vec, which is robust against noise and takes only linear time to compute the similarity between two sports plays. We conduct experiments on real-world soccer match data, and the results show that our solution performs more effectively and efficiently compared with the state-of-the-art methods.