The size of spatial data is growing intensively due to the emergence of and the tremendous advances in technology such as sensors and the internet of things. Supporting high-performance queries on this large volume of data becomes essential in several data- and compute-intensive applications. Unfortunately, most of the existing methods and approaches are based on a traditional computing framework (uniprocessors) which makes them not scalable and not adequate to deal with large-scale data. In this work, we present a high-performance query for massive spatio–temporal data. The query consists of selecting fixed size raster subsequences, based on the average of their region of interest, from a spatio–temporal raster sequence satisfying a user threshold condition. In our paper, for the purpose of simplification, we consider that the region of interest is the entire raster and not only a subregion. Our aim is to speed up the execution using parallel primitives and pure CUDA. Furthermore, we propose a new method based on a sorting step to save computations and boost the speed of the query execution. The test results show that the proposed methods are faster and good performance is achieved even with large-scale rasters and data.