Spatio-temporal Predictive Queries encompass a spatio tem- poral constraint, defining a region, a target variable, and an evaluation metric. The output of such queries presents the future values for the tar- get variable computed by predictive models at each point of the spatio- temporal region. Unfortunately, especially for large spatio-temporal do- mains with millions of points, training temporal models at each spatial domain point is prohibitive. In this work, we propose a data-driven ap- proach for selecting pre-trained temporal models to be applied at each query point. The chosen approach applies a model to a point according to the training and input time series similarity. The approach avoids train- ing a different model for each domain point, saving model training time. Moreover, it provides a technique to decide on the best-trained model to be applied to a point for prediction. In order to assess the applicability of the proposed strategy, we evaluate a case study for temperature fore- casting using historical data and auto-regressive models. Computational experiments show that the proposed approach, compared to the base- line, achieves equivalent predictive performance using a composition of pre-trained models at a fraction of the total computational cost.