This experimental study assesses the ability of variational autoencoders (VAEs) to perform anomaly detection in clinical routine, in particular the detection of age-related white matter lesions in brain MRIs acquired at different hospitals and gathered in a clinical data warehouse (CDW). We pre-trained a state-of-the-art -VAE on a healthy cohort of over 10,000 FLAIR MR images from the UK Biobank to learn the distribution of healthy brains. The model was then fine-tuned on a cohort of nearly 700 healthy FLAIR images coming from a CDW. We first ensured the good performance of our pre-trained model compared with the state-of-the-art using a widely used public dataset (MSSEG). We then validated it on our target task, age-related WMH detection, on ADNI3 and on a curated clinical dataset from a single-site neuroradiology department, for which we had manually delineated lesion masks. Next, we applied the fine-tuned -VAE for anomaly detection in a CDW characterised by an exceptional heterogeneity in terms of hospitals, scanners and image quality. We found a correlation between the Fazekas scores extracted from the radiology reports and the volumes of the lesions detected by our model, providing a first insight into the performance of VAEs in a clinical setting. We also observed that our model was robust to image quality, which strongly varies in the CDW. However, despite these encouraging results, such approach is not ready for an application in clinical routine yet due to occasional failures in detecting certain lesions, primarily attributed to the poor quality of the images reconstructed by the VAE.