This master thesis investigates co-location patterns: categories of entities that frequently appear close to each other. In the co-location pattern mining problem, the categories are called features and each entity that belongs to a specific category is named instance. In the urban field, an example can be "John's Restaurant" which is an instance of the feature "Restaurant". Co-location patterns are important since they reveal underlying correlations between entities. Several algorithms were proposed in literature to tackle the spatial co-location mining task. A step forward in state-of-the-art methods consists in implementing parallel approaches. The idea behind it is to divide the entire dataset into independent partitions that will be processed in parallel.