In recent years, many industries have utilized machine learning (ML) models in their systems. Ideally, ML models should be trained on and applied to data from the same distributions. However, the data evolves over time in many applications, leading to concept drift, which in turn causes the ML model performance to degrade. Therefore, maintaining up-to-date ML models plays a critical role in the MLOps pipeline. Existing ML model maintenance approaches are often computationally resource-intensive, costly, time-consuming, and model-dependent. Thus, we propose an improved MLOps pipeline, a new model maintenance approach and a Similarity-Based Model Reuse tool to address the challenges of ML model maintenance. We identify seasonal and recurrent data distribution patterns in time series datasets. Recurrent data distribution patterns enable us to reuse previously trained models for similar distributions in the future, thus avoiding unnecessary retrainings. Then, we integrate the model reuse approach into the MLOps pipeline and propose our improved MLOps pipeline. Furthermore, we develop a tool that stores and reuses models for inference on future data with similar distributions. Experiments on five datasets show that our model reuse approach preserves performance while cutting maintenance costs by 87.5%, offering a cost-effective solution for maintaining ML model performance in deployment.